docling-project / docling-project/docling

Expected time converting a 20 pages paper

Open
#2,524 4 comments 0 reactions 0 assignees View on GitHub
question
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

I'm trying to convert a 21-page PDF using Docling on H100 GPUs. However, the process is very slow, and I had to stop it manually. What is the expected processing time? Also, how can I speed it up? I noticed the GPU utilization stays very low (around 3%–5%) during conversion.

```python
from docling_core.types.doc import ImageRefMode, PictureItem, TableItem

from docling.datamodel.base_models import InputFormat, BoundingBox
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.datamodel.settings import settings

IMAGE_RESOLUTION_SCALE = 5.0

pipeline_options = PdfPipelineOptions()
pipeline_options.images_scale = IMAGE_RESOLUTION_SCALE
pipeline_options.generate_page_images = True
pipeline_options.generate_picture_images = True
pipeline_options.do_formula_enrichment = True # Enable formula enrichment

doc_converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
}
)

settings.debug.profile_pipeline_timings = True
raw_result = doc_converter.convert("/share/project/luoxin/projects2/EvoPresent/paper_input/EditScore/paper.pdf")

doc_conversion_secs = raw_result.timings["pipeline_total"].times
print(f"Conversion secs: {doc_conversion_secs}")
```

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.